New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Scaling Error when training using different ratio size of image in batch_size > 1 #8
Comments
Oh... I guess the rescale function is not working perfectly... I will fix it. By the way, you used image size(200, 200) using PSPnet. I don't know your dataset, but PSPnet needs a bigger size than other networks because the network has a pyramid structure. There is some chance to vanish feature. If you don't know about that, test it :) |
Ah thank you! I guess that's why it's not working well in some of my cases with small pixel label (ie. detecting crack), but doing well in some case with large label area (road, house, etc). |
Well, FCN is a simple network and requires lower GPU resources than other networks. You can use this network when you have not good enough hardware like a mobile phone.
I hope it can help you. Thanks. |
Error in
Trainer.train()
RuntimeError: stack expects each tensor to be equal size, but got [3, 200, 257] at entry 0 and [3, 200, 341] at entry 2
When using set of image that contain different kind of ratio (for example 4:3 with 16:9).
Running in batch_size = 1 is fine. But larger than that, make this error.
Sorry for troubling you haha.
It's not really a bug I guess, I can solve it by resizing the train image myself, just letting you know if you want to fix it.
The text was updated successfully, but these errors were encountered: